mlsanityData to 7 Oct 2026

Adapting to Length Shift: FlexiLength Network for Trajectory Prediction

arXiv 2404.00742 ↗First posted 31 Mar 2024cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a standardized input duration. However, a notable issue arises when these models are evaluated with varying observation lengths, leading to a significant performance drop, a phenomenon we term the Observation Length Shift. To address this issue, we introduce a general and effective framework, the FlexiLength Network (FLN), to enhance the robustness of existing trajectory prediction techniques against varying observation periods. Specifically, FLN integrates trajectory data with diverse observation lengths, incorporates FlexiLength Calibration (FLC) to acquire temporal invariant representations, and employs FlexiLength Adaptation (FLA) to further refine these representations for more accurate future trajectory predictions. Comprehensive experiments on multiple datasets, ie, ETH/UCY, nuScenes, and Argoverse 1, demonstrate the effectiveness and flexibility of our proposed FLN framework.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 56 of its 76 references that are in the map. First posted on arXiv 31 Mar 2024.

Builds on

56 of 76 references.

References · 56

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  4. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  5. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  6. 2022Planning-oriented Autonomous Drivingcited by 1,068
  7. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  8. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  9. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  10. 2018Universal Transformerscited by 613
  11. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  12. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 324
38 more
  1. 2018Slimmable Neural Networkscited by 301
  2. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 299
  3. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  4. 2019Theoretical Limitations of Self-Attention in Neural Sequence Modelscited by 286
  5. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
  6. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  7. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  8. 2019Universally Slimmable Networks and Improved Training Techniquescited by 219
  9. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  10. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 210
  11. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 184
  12. 2020Transformer Networks for Trajectory Forecastingcited by 180
  13. 2023MotionLM: Multi-Agent Motion Forecasting as Language Modelingcited by 154
  14. 2023Leapfrog Diffusion Model for Stochastic Trajectory Predictioncited by 129
  15. 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
  16. 2022ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queriescited by 116
  17. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  18. 2022Remember Intentions: Retrospective-Memory-based Trajectory Predictioncited by 86
  19. 2019Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANscited by 78
  20. 2019Conditional Generative Neural System for Probabilistic Trajectory Predictioncited by 76
  21. 2020Recursive Social Behavior Graph for Trajectory Predictioncited by 66
  22. 2022SocialVAE: Human Trajectory Prediction using Timewise Latentscited by 65
  23. 2022Adaptive Trajectory Prediction via Transferable GNNcited by 51
  24. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  25. 2023Leveraging Future Relationship Reasoning for Vehicle Trajectory Predictioncited by 47
  26. 2022Learning Pedestrian Group Representations for Multi-modal Trajectory Predictioncited by 44
  27. 2023Traj-MAE: Masked Autoencoders for Trajectory Predictioncited by 42
  28. 2022FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphscited by 41
  29. 2023EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecastingcited by 41
  30. 2021Vehicle trajectory prediction works, but not everywherecited by 39
  31. 2023ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptationcited by 39
  32. 2022Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Predictioncited by 36
  33. 2022How many Observations are Enough? Knowledge Distillation for Trajectory Forecastingcited by 35
  34. 2022Goal-driven Self-Attentive Recurrent Networks for Trajectory Predictioncited by 28
  35. 2022Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learningcited by 23
  36. 2023Unsupervised Sampling Promoting for Stochastic Human Trajectory Predictioncited by 17
  37. 2023Human-centric Scene Understanding for 3D Large-scale Scenarioscited by 17
  38. 2023Scene Informer: Anchor-based Occlusion Inference and Trajectory Prediction in Partially Observable Environmentscited by 14

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 13; 2026: 6.

22 papers.

Sort:

By area:

  1. 2024Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sportscited by 19
  2. 2025Multi-modal Knowledge Distillation-based Human Trajectory Forecastingcited by 10
  3. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  4. 2025Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Modelcited by 6
  5. 2024Resonance: Learning to Predict Social-Aware Pedestrian Trajectories as Co-Vibrationscited by 5
  6. 2025Beyond Patterns: Harnessing Causal Logic for Autonomous Driving Trajectory Predictioncited by 4
  7. 2025AMD: Adaptive Momentum and Decoupled Contrastive Learning Framework for Robust Long-Tail Trajectory Predictioncited by 4
  8. 2025Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planningcited by 4
  9. 2025OmniTraj: Pre-Training on Heterogeneous Data for Adaptive and Zero-Shot Human Trajectory Predictioncited by 3
  10. 2024RealTraj: Towards Real-World Pedestrian Trajectory Forecastingcited by 2
  11. 2025STEP: Structured Training and Evaluation Platform for benchmarking trajectory prediction modelscited by 2
  12. 2026Recover to Predict: Progressive Retrospective Learning for Variable-Length Trajectory Predictioncited by 2
10 more
  1. 2025Adaptive Output Steps: FlexiSteps Network for Dynamic Trajectory Predictioncited by 1
  2. 2025Addressing Corner Cases in Autonomous Driving: A World Model-based Approach with Mixture of Experts and LLMscited by 1
  3. 2025Reverberation: Learning the Latencies Before Forecasting Trajectoriescited by 1
  4. 2025AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sportscited by 0
  5. 2025Hazy Pedestrian Trajectory Prediction via Physical Priors and Graph-Mambacited by 0
  6. 2026TaPD: Temporal-adaptive Progressive Distillation for Observation-Adaptive Trajectory Forecasting in Autonomous Drivingcited by 0
  7. 2026SHARP: Short-Window Streaming for Accurate and Robust Prediction in Motion Forecastingcited by 0
  8. 2026SAIL: Scene-aware Adaptive Iterative Learning for Long-Tail Trajectory Prediction in Autonomous Vehiclescited by 0
  9. 2026EdgeVTP: Exploration of Latency-efficient Trajectory Prediction for Edge-based Embedded Vision Applicationscited by 0
  10. 2026Encore: Conditioning Trajectory Forecasting via Biased Ego Rehearsalscited by 0